Unsupervised Anomaly Detection and Localization with Generative Adversarial Networks

Conference: ECOC 2024 - 50th European Conference on Optical Communication
09/22/2024 - 09/26/2024 at Frankfurt, Germany

Proceedings: ITG-Fb. 317: ECOC 2024

Pages: 4Language: englishTyp: PDF

Authors:
Abdelli, Khouloud; Lonardi, Matteo; Gripp, Jurgen; Olsson, Samuel; Boitier, Fabien; Layec, Patricia

Abstract:
We propose a novel unsupervised anomaly detection approach using generative adversarial networks and SOP-derived spectrograms. Demonstrating remarkable efficacy, our method achieves over 97% accuracy on SOP datasets from both submarine and terrestrial fiber links, all achieved without the need for labelled data.